SkillVaultskills Browse all 1,000+ skills

People Operations · Version 1.0.0 · Reviewed 2026-08-02

Performance Feedback Writer

Make evidence grounding and behavioral specificity with evidence, explicit trade-offs, and a verification plan.

4 method steps 4 documented failure modes 4 diagnostic checks 7 quality gates

Writes specific, behavioral, actionable feedback grounded in observed evidence rather than impressions.

₹299 one-time

Get this skill archive

Install in your AI coding tool

SkillVault packages this skill in the open Agent Skills format for five leading coding tools, with a raw SKILL.md fallback for every other compatible IDE or agent.

See the complete graphical installation and usage guide

What this skill helps you do

  • Evidence grounding
  • Behavioral specificity
  • Actionability

How Performance Feedback Writer works

You provide

Interview notes, rubric, or survey data with response rates

It inspects

Evidence specificity and rubric consistency for evidence grounding

It decides

A behavioral specificity judgment with gaps marked rather than guessed

You verify

Score distributions compared across evaluators for drift

What it checks first

Performance Feedback Writer writes specific, behavioral, actionable feedback grounded in observed evidence rather than impressions. Use it when the work involves Evidence grounding, Behavioral specificity, Actionability.

  1. Whether evaluation evidence is behavioral and specific or impressionistic.
  2. Whether the same standard was applied across candidates or drifted between them.
  3. Sample size and anonymity conditions behind any survey conclusion.
  4. Whether a theme reflects a widespread issue or a small vocal group.

Failure modes it recognizes

  • Scores assigned before evidence is recorded, so the evidence is written to justify the score.
  • Free-text survey themes dominated by the most articulate respondents rather than the most common view.
  • Comparison across interviewers who applied different implicit bars.
  • Anonymity promised but breakable through small-group segmentation.

Answers it will reject

  • Reporting sentiment percentages from a low-response survey as if representative.
  • Using a rubric as decoration while the decision is made on overall impression.
  • Aggregating feedback in a way that identifies individuals in small teams.

Decision rules it applies

  • Record the behavioral evidence before assigning any score.
  • Apply one rubric consistently and flag where evidence is insufficient rather than guessing.
  • Protect anonymity by suppressing segments below a minimum response threshold.

Evidence it asks for

  • Compare score distributions across interviewers to detect a drifting bar.
  • Report response rate and denominator alongside every survey finding.
  • Attach representative verbatims to each theme without identifying detail.

The method inside

  1. Define the decision criterion before reading the evidence
  2. Separate observation from interpretation and bias
  3. Check consistency across people, segments, or reviewers
  4. Produce actionable language while preserving confidentiality

Deliverables

  • Evidence grounding evidence assessment
  • Behavioral specificity consistency findings
  • Actionability action-ready revision

Evidence requirements

  • Role rubric, policy, survey, or review artifact
  • Observable behavior and outcomes
  • Relevant context with unnecessary personal identifiers removed

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Turn these notes into performance feedback. The theme is that this engineer needs to communicate better.

Expected output

Communicate better is not actionable because it names no behavior and no context. Find the specific situations in the notes, describe what happened and its effect, and state the observable change you expect; anything less will be interpreted as a personality judgment...

Boundaries and compatibility

Ideal for

  • Evidence grounding: produce a decision or artifact grounded in supplied evidence.
  • Behavioral specificity: produce a decision or artifact grounded in supplied evidence.
  • Actionability: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Making employment decisions without accountable human review
  • Inferring protected characteristics or psychological states

Agent compatibility

  • GitHub Copilot Agent Skills
  • Cursor Agent Skills
  • Claude Code Skills
  • OpenAI Codex Skills
  • JetBrains Junie Skills

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.